speckit-analyze

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill exhibits no malicious patterns. Its operations are consistent with its stated purpose of software architecture analysis.
  • [COMMAND_EXECUTION]: The skill executes a local PowerShell script (.specify/scripts/powershell/check-prerequisites.ps1) to initialize project context and verify the existence of required artifacts. This is a functional requirement for the speckit framework and does not involve external network calls or privilege escalation.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes content from project artifacts (spec.md, plan.md, tasks.md) that could be modified by third parties. However, the risk is minimized by the skill's read-only constraints and its focus on semantic modeling rather than direct instruction execution from data.
  • Ingestion points: Local files: spec.md, plan.md, tasks.md, and .specify/memory/constitution.md.
  • Boundary markers: None explicitly implemented; the agent relies on structured parsing instructions.
  • Capability inventory: File system read access and local PowerShell script execution.
  • Sanitization: No explicit sanitization or escaping of ingested data is specified before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 02:49 PM
Security Audit — agent-trust-hub — speckit-analyze